机器学习29:Sklearn库常用分类器及效果比较

2024-07-11 11:16| 来源: 网络整理| 查看: 265

1.Sklearn库常用分类器：

#【1】 KNN Classifier # k-近邻分类器 from sklearn.neighbors import KNeighborsClassifier clf = KNeighborsClassifier() clf.fit(train_x, train_y) #【2】 Logistic Regression Classifier # 逻辑回归分类器 from sklearn.linear_model import LogisticRegression clf = LogisticRegression(penalty='l2') clf.fit(train_x, train_y) #【3】 Random Forest Classifier # 随机森林分类器 from sklearn.ensemble import RandomForestClassifier clf = RandomForestClassifier(n_estimators=8) clf.fit(train_x, train_y) #【4】 Decision Tree Classifier # 决策树分类器 from sklearn import tree clf = tree.DecisionTreeClassifier() clf.fit(train_x, train_y) #【5】 SVM Classifier # 支持向量机分类器 from sklearn.svm import SVC clf = SVC(kernel='rbf', probability=True) clf.fit(train_x, train_y) #【6】 Multinomial Naive Bayes Classifier # 多项式朴素贝叶斯分类器 from sklearn.naive_bayes import MultinomialNB clf = MultinomialNB(alpha=0.01) clf.fit(train_x, train_y) #【7】 GBDT(Gradient Boosting Decision Tree) Classifier # 梯度增强决策树分类器 from sklearn.ensemble import GradientBoostingClassifier clf = GradientBoostingClassifier(n_estimators=200) clf.fit(train_x, train_y) #【8】AdaBoost Classifier from sklearn.ensemble import AdaBoostClassifier clf = AdaBoostClassifier() clf.fit(train_x, train_y) #【9】 GaussianNB # 高斯贝叶斯分类器 from sklearn.naive_bayes import GaussianNB clf = GaussianNB() clf.fit(train_x, train_y) #【10】 Linear Discriminant Analysis # 线性判别分析 from sklearn.discriminant_analysis import LinearDiscriminantAnalysis clf = LinearDiscriminantAnalysis() clf.fit(train_x, train_y) #【11】 Quadratic Discriminant Analysis # 二次判别分析 from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis clf = QuadraticDiscriminantAnalysis() clf.fit(train_x, train_y)

2.Slearn常见分类器的效果比较：

本段代码摘抄自Sklearn常见分类起的效果比较，效果图可以点进原文查看，也可以在python上运行查看。

import numpy as np import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.datasets import make_moons, make_circles, make_classification from sklearn.neural_network import BernoulliRBM from sklearn.neighbors import KNeighborsClassifier from sklearn.svm import SVC # from sklearn.gaussian_process import GaussianProcess from sklearn.tree import DecisionTreeClassifier from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier from sklearn.naive_bayes import GaussianNB from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis h = .02 # step size in the mesh names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree", "Random Forest", "AdaBoost", "Naive Bayes", "QDA", "Gaussian Process","Neural Net", ] classifiers = [ KNeighborsClassifier(3), SVC(kernel="linear", C=0.025), SVC(gamma=2, C=1), DecisionTreeClassifier(max_depth=5), RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1), AdaBoostClassifier(), GaussianNB(), QuadraticDiscriminantAnalysis(), #GaussianProcess(), #BernoulliRBM(), ] X, y = make_classification(n_features=2, n_redundant=0, n_informative=2, random_state=1, n_clusters_per_class=1) rng = np.random.RandomState(2) X += 2 * rng.uniform(size=X.shape) linearly_separable = (X, y) datasets = [make_moons(noise=0.3, random_state=0), make_circles(noise=0.2, factor=0.5, random_state=1), linearly_separable ] figure = plt.figure(figsize=(27, 9)) i = 1 # iterate over datasets for ds_cnt, ds in enumerate(datasets): # preprocess dataset, split into training and test part X, y = ds X = StandardScaler().fit_transform(X) X_train, X_test, y_train, y_test = \ train_test_split(X, y, test_size=.4, random_state=42) x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5 y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5 xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h)) # just plot the dataset first cm = plt.cm.RdBu cm_bright = ListedColormap(['#FF0000', '#0000FF']) ax = plt.subplot(len(datasets), len(classifiers) + 1, i) if ds_cnt == 0: ax.set_title("Input data") # Plot the training points ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright) # and testing points ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6) ax.set_xlim(xx.min(), xx.max()) ax.set_ylim(yy.min(), yy.max()) ax.set_xticks(()) ax.set_yticks(()) i += 1 # iterate over classifiers for name, clf in zip(names, classifiers): ax = plt.subplot(len(datasets), len(classifiers) + 1, i) clf.fit(X_train, y_train) score = clf.score(X_test, y_test) # Plot the decision boundary. For that, we will assign a color to each # point in the mesh [x_min, m_max]x[y_min, y_max]. if hasattr(clf, "decision_function"): Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()]) else: Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1] # Put the result into a color plot Z = Z.reshape(xx.shape) ax.contourf(xx, yy, Z, cmap=cm, alpha=.8) # Plot also the training points ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright) # and testing points ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6) ax.set_xlim(xx.min(), xx.max()) ax.set_ylim(yy.min(), yy.max()) ax.set_xticks(()) ax.set_yticks(()) if ds_cnt == 0: ax.set_title(name) ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'), size=15, horizontalalignment='right') i += 1 plt.tight_layout() plt.show()

【本文地址】

公司简介

联系我们